[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75QZHZ0FNJCXPR0YRV6HD23":3,"skill-same:01M75QZHZ0FNJCXPR0YRV6HD23":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75QZHZ0FNJCXPR0YRV6HD23","belfry-debug",null,"Use Belfry to set up local observability, export OpenTelemetry traces or logs, or debug a Service through bounded searches and exact trace\u002Fspan\u002Flog correlations.","endalk200\u002Fbelfry","endalk200","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F44495881?v=4","01M6BYRJ2PAY7EXZ7DJF5VZ7DB","Endalkachew Biruk","01M75QXWNV09P171XEQ9K63NQS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002Fskills\u002Fbelfry-debug\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: belfry-debug\ndescription: Use Belfry to set up local observability, export OpenTelemetry traces or logs, or debug a Service through bounded searches and exact trace\u002Fspan\u002Flog correlations.\n---\n\n# Belfry\n\nEstablish a **telemetry handshake**, then follow the **evidence trail**.\n\nBelfry is a local-development workbench. Use its verified Daemon endpoint and\nbounded Query API; treat the shared SQLite Telemetry Store as an implementation\ndetail. Keep telemetry on loopback and redact sensitive values before export.\n\n## 1. Establish the Daemon endpoint\n\nResolve the command before running it:\n\n- In the Belfry source repository, use `bun run belfry --`.\n- Elsewhere, use an installed `belfry`.\n\nRun `daemon status --json`. When it is stopped, run `daemon start --json`.\nCapture the `endpoint` from the JSON instead of assuming the default port, then\nrequest `GET {endpoint}\u002Fapi\u002Fhealth`.\n\nWhen Belfry is absent, configuration is invalid, the endpoint is unknown, or a\ntarget Service is not visible yet, read\n[setup and export](references\u002Fsetup-and-export.md) completely before changing\ninstrumentation.\n\nComplete this step when the verified endpoint is recorded, `live` is `true`,\nand the health response establishes whether `writerReady` and `readsAvailable`\npermit the next operation.\n\n## 2. Prove the telemetry handshake\n\nBefore exercising the target, snapshot `GET \u002Fapi\u002Fingestion\u002Fstats`. Run one\nrecognizable operation, flush the enabled exporters, and request the statistics\nagain. Then list Services over the same time window.\n\nBefore the bounded Service request, read\n[the Query API reference](references\u002Fquery-api.md) completely for time\nconstruction, required fields, and cursor rules.\n\nFor every enabled signal:\n\n- its accepted-record counter increased;\n- rejected\u002Fdecode counters did not unexpectedly increase;\n- the exact Service identity `(namespace, name, environment)` appeared.\n\nWhen a counter or Service does not move, read\n[troubleshooting](references\u002Ftroubleshooting.md) completely and locate the\nbreak before searching wider.\n\nComplete this step when every expected signal is committed and discoverable, or\nwhen the first broken layer is identified with health, counter, diagnostic, or\nexporter evidence.\n\n## 3. Bound the investigation\n\nRecord the symptom, expected behavior, target Service, and the narrowest useful\nnanosecond window. Preserve exact IDs and timestamps from the failure. Prefer a\nknown trace ID, span ID, log ID, operation, error text, or domain attribute over\nan unbounded text search.\n\nUse [the Query API reference](references\u002Fquery-api.md) for request payloads,\nsearch projections, and response semantics. Treat\n`{endpoint}\u002Fopenapi.json` as authoritative when the running version differs\nfrom the reference.\n\nComplete this step when the endpoint, Service Filter, time bounds, and sharpest\nknown identifier are explicit.\n\n## 4. Follow the evidence trail\n\nChoose the entry point that matches the evidence:\n\n- **Trace-first:** search traces, select an exact candidate, open its detail,\n  inspect the failing span, then load trace- or span-correlated logs.\n- **Log-first:** search logs, open each relevant log detail, then open its exact\n  trace and span when correlation IDs are present.\n- **Identity-first:** open a known trace, span, or log directly.\n\nFor a trace, record its root operation, participating Services, active state,\nerrors, structural warnings, and `spansTruncated`. Inspect error spans, events,\nlinks, attributes, resource, scope, and `logCount`. Use the dedicated span\nendpoint when trace detail is truncated or one span needs complete inspection.\n\nFor logs, distinguish exact correlation from temporal inference. A shared trace\nID, and optionally span ID, is exact. Similar timestamps, text, or attributes\nwithout shared IDs are supporting evidence only.\n\nFollow every page while `truncated` is `true`. Replay the identical endpoint,\nfilters, bounds, limit, and sort with only `cursor` added; signed cursors cannot\nbe reused with a changed query.\n\nComplete this step when one exact causal path is supported across trace, span,\nand logs, or every bounded candidate and correlation page is exhausted and the\nremaining absence is explicit.\n\n## 5. Report evidence\n\nReport:\n\n- Daemon endpoint and health gates;\n- query bounds, filters, sort, and exhausted pages;\n- Service identities;\n- trace, span, and log IDs with exact nanosecond timestamps;\n- ingestion diagnostics or counter deltas relevant to missing data;\n- observations, separately labelled hypotheses, and unresolved gaps.\n\nComplete the investigation only when every conclusion cites reported telemetry\nevidence or is explicitly marked as a hypothesis or unresolved.\n","# Belfry\n\nEstablish a **telemetry handshake**, then follow the **evidence trail**.\n\nBelfry is a local-development workbench. Use its verified Daemon endpoint and\nbounded Query API; treat the shared SQLite Telemetry Store as an implementation\ndetail. Keep telemetry on loopback and redact sensitive values before export.\n\n## 1. Establish the Daemon endpoint\n\nResolve the command before running it:\n\n- In the Belfry source repository, use `bun run belfry --`.\n- Elsewhere, use an installed `belfry`.\n\nRun `daemon status --json`. When it is stopped, run `daemon start --json`.\nCapture the `endpoint` from the JSON instead of assuming the default port, then\nrequest `GET {endpoint}\u002Fapi\u002Fhealth`.\n\nWhen Belfry is absent, configuration is invalid, the endpoint is unknown, or a\ntarget Service is not visible yet, read\n[setup and export](references\u002Fsetup-and-export.md) completely before changing\ninstrumentation.\n\nComplete this step when the verified endpoint is recorded, `live` is `true`,\nand the health response establishes whether `writerReady` and `readsAvailable`\npermit the next operation.\n\n## 2. Prove the telemetry handshake\n\nBefore exercising the target, snapshot `GET \u002Fapi\u002Fingestion\u002Fstats`. Run one\nrecognizable operation, flush the enabled exporters, and request the statistics\nagain. Then list Services over the same time window.\n\nBefore the bounded Service request, read\n[the Query API reference](references\u002Fquery-api.md) completely for time\nconstruction, required fields, and cursor rules.\n\nFor every enabled signal:\n\n- its accepted-record counter increased;\n- rejected\u002Fdecode counters did not unexpectedly increase;\n- the exact Service identity `(namespace, name, environment)` appeared.\n\nWhen a counter or Service does not move, read\n[troubleshooting](references\u002Ftroubleshooting.md) completely and locate the\nbreak before searching wider.\n\nComplete this step when every expected signal is committed and discoverable, or\nwhen the first broken layer is identified with health, counter, diagnostic, or\nexporter evidence.\n\n## 3. Bound the investigation\n\nRecord the symptom, expected behavior, target Service, and the narrowest useful\nnanosecond window. Preserve exact IDs and timestamps from the failure. Prefer a\nknown trace ID, span ID, log ID, operation, error text, or domain attribute over\nan unbounded text search.\n\nUse [the Query API reference](references\u002Fquery-api.md) for request payloads,\nsearch projections, and response semantics. Treat\n`{endpoint}\u002Fopenapi.json` as authoritative when the running version differs\nfrom the reference.\n\nComplete this step when the endpoint, Service Filter, time bounds, and sharpest\nknown identifier are explicit.\n\n## 4. Follow the evidence trail\n\nChoose the entry point that matches the evidence:\n\n- **Trace-first:** search traces, select an exact candidate, open its detail,\n  inspect the failing span, then load trace- or span-correlated logs.\n- **Log-first:** search logs, open each relevant log detail, then open its exact\n  trace and span when correlation IDs are present.\n- **Identity-first:** open a known trace, span, or log directly.\n\nFor a trace, record its root operation, participating Services, active state,\nerrors, structural warnings, and `spansTruncated`. Inspect error spans, events,\nlinks, attributes, resource, scope, and `logCount`. Use the dedicated span\nendpoint when trace detail is truncated or one span needs complete inspection.\n\nFor logs, distinguish exact correlation from temporal inference. A shared trace\nID, and optionally span ID, is exact. Similar timestamps, text, or attributes\nwithout shared IDs are supporting evidence only.\n\nFollow every page while `truncated` is `true`. Replay the identical endpoint,\nfilters, bounds, limit, and sort with only `cursor` added; signed cursors cannot\nbe reused with a changed query.\n\nComplete this step when one exact causal path is supported across trace, span,\nand logs, or every bounded candidate and correlation page is exhausted and the\nremaining absence is explicit.\n\n## 5. Report evidence\n\nReport:\n\n- Daemon endpoint and health gates;\n- query bounds, filters, sort, and exhausted pages;\n- Service identities;\n- trace, span, and log IDs with exact nanosecond timestamps;\n- ingestion diagnostics or counter deltas relevant to missing data;\n- observations, separately labelled hypotheses, and unresolved gaps.\n\nComplete the investigation only when every conclusion cites reported telemetry\nevidence or is explicitly marked as a hypothesis or unresolved.\n",{"name":5,"description":7},"main","85147901ef9b123a45845969897388075a0aa06e","skills\u002Fbelfry-debug",0,"https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry","https:\u002F\u002Fgithub.com\u002Fendalk200","endalk200.com","Senior Software Engineer & Technical Lead","2026-10-23 13:50:38",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add endalk200\u002Fbelfry --skill belfry-debug",{"tool":39,"command":40},"bunx","bunx skills add endalk200\u002Fbelfry --skill belfry-debug",{"tool":42,"command":43},"pnpm","pnpm dlx skills add endalk200\u002Fbelfry --skill belfry-debug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002Fskills\u002Fbelfry-debug\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fquery-api.md","REFERENCE","参考文档",7141,"https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002Fskills\u002Fbelfry-debug\u002Freferences\u002Fquery-api.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fsetup-and-export.md",9034,"https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002Fskills\u002Fbelfry-debug\u002Freferences\u002Fsetup-and-export.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5511,"https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002Fskills\u002Fbelfry-debug\u002Freferences\u002Ftroubleshooting.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M75QZGBVJCCXJV8275C1HRSA","writing-great-skills","Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75QZE6TNFJ93H0KCT540D22","wayfinder","Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M75QZ710J3QJY7218T4NEGVA","turborepo","Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines,\ndependsOn, caching, remote cache, the \"turbo\" CLI, --filter, --affected, CI optimization, environment\nvariables, internal packages, monorepo structure\u002Fbest practices, and boundaries.\n\nUse when user: configures tasks\u002Fworkflows\u002Fpipelines, creates packages, sets up\nmonorepo, shares code between apps, runs changed\u002Faffected packages, debugs cache,\nor has apps\u002Fpackages directories.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fturborepo\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75QZ40HE8VT1FZ29QBTESN8","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in a local file, or native blocking links on a real tracker.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M75QZ27CMMP1VA68F8HNMGNF","to-spec","Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fto-spec\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M75QZ0G91S0ECY16A8DBSWQQ","tdd","Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions \"red-green-refactor\", or wants integration tests.","https:\u002F\u002Fgithub.com\u002Fendalk200\u002Fbelfry\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]